def __init__(self):
label_map_file = self.load_labelemap()
label_map = label_map_util.load_labelmap(label_map_file)
log.debug(label_map)
categories = label_map_util.convert_label_map_to_categories(
label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
self.__category_index = label_map_util.create_category_index(
categories)
self.__detection_graph = tf.Graph()
#self.__feature_extractor = ExtractFeature(use_gpu=True)
self.__color_extractor = ExtractColor(use_gpu=True)
model_file = self.load_model()
with self.__detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(model_file, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
with tf.device(GPU):
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
self.__sess = tf.Session(config=config,
graph=self.__detection_graph)
log.info('_init_ done')
def __init__(self):
label_map = label_map_util.load_labelmap(OD_LABELS)
log.debug(label_map)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES,
use_display_name=True)
self.__category_index = label_map_util.create_category_index(categories)
self.__detection_graph = tf.Graph()
with self.__detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(OD_MODEL, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
self.__sess = tf.Session(graph=self.__detection_graph)
self.image_feature = ExtractFeature()
log.info('_init_ done')
def __init__(self):
# Load categories
curr_dir = os.path.dirname(os.path.realpath(__file__))
labels_file = curr_dir + '/label_map.pbtxt'
num_classes = 14
label_map = label_map_util.load_labelmap(labels_file)
categories = label_map_util.convert_label_map_to_categories(
label_map, max_num_classes=num_classes, use_display_name=True)
self.category_index = label_map_util.create_category_index(categories)
# Load inference graph
frozen_graph_file = curr_dir + '/inference_graph/frozen_inference_graph.pb'
self.detection_graph = tf.Graph()
with self.detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(frozen_graph_file, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
self.sess = tf.Session(graph=self.detection_graph, config=config)
# Input and output tensors
self.image_tensor = self.detection_graph.get_tensor_by_name(
'image_tensor:0')
self.detection_boxes = self.detection_graph.get_tensor_by_name(
'detection_boxes:0')
self.detection_scores = self.detection_graph.get_tensor_by_name(
'detection_scores:0')
self.detection_classes = self.detection_graph.get_tensor_by_name(
'detection_classes:0')
self.num_detections = self.detection_graph.get_tensor_by_name(
'num_detections:0')
self.debug = False
def __init__(self):
# self.download_model()
# Loading label map
self.__api_instance = stylelens_index.ImageApi()
self.__search = stylelens_search.SearchApi()
label_map = label_map_util.load_labelmap(OD_LABELS)
print(label_map)
categories = label_map_util.convert_label_map_to_categories(
label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
self.__category_index = label_map_util.create_category_index(
categories)
self.__detection_graph = tf.Graph()
with self.__detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(OD_MODEL, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
self.__sess = tf.Session(graph=self.__detection_graph)
self.image_feature = feature_extract.ExtractFeature()
print('_init_ done')
CURRENCY_UNIT = 'currency_unit'
PRODUCT_URL = 'product_url'
PRODUCT_NO = 'product_no'
MAIN = 'main'
NATION = 'nation'
REDIS_IMAGE_CROP_QUEUE = 'bl:image:crop:queue'
STR_BUCKET = "bucket"
STR_STORAGE = "storage"
STR_CLASS_CODE = "class_code"
STR_NAME = "name"
STR_FORMAT = "format"
# Loading label map
label_map = label_map_util.load_labelmap(OD_LABELS)
categories = label_map_util.convert_label_map_to_categories(
label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
api_instance = stylelens_index.ImageApi()
REDIS_SERVER = os.environ['REDIS_SERVER']
rconn = redis.StrictRedis(REDIS_SERVER)
logging.basicConfig(filename='./log/main.log', level=logging.DEBUG)
heart_bit = True
def job():
file_name = os.path.basename(file.name)
if 'frozen_inference_graph.pb' in file_name:
tar_file.extract(file, os.getcwd())
# ## Load a (frozen) Tensorflow model into memory.
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
# ## Loading label map
# Label maps map indices to category names, so that when our convolution network predicts `5`, we know that this corresponds to `airplane`. Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(
label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
# ## Helper code
def load_image_into_numpy_array(image):
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape(
(im_height, im_width, 3)).astype(np.uint8)
# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)